acryl-datahub 1.1.1rc4__py3-none-any.whl → 1.3.0.1rc9__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of acryl-datahub might be problematic. Click here for more details.

Files changed (414) hide show
  1. {acryl_datahub-1.1.1rc4.dist-info → acryl_datahub-1.3.0.1rc9.dist-info}/METADATA +2615 -2547
  2. {acryl_datahub-1.1.1rc4.dist-info → acryl_datahub-1.3.0.1rc9.dist-info}/RECORD +412 -338
  3. {acryl_datahub-1.1.1rc4.dist-info → acryl_datahub-1.3.0.1rc9.dist-info}/entry_points.txt +5 -0
  4. datahub/_version.py +1 -1
  5. datahub/api/entities/assertion/assertion.py +1 -1
  6. datahub/api/entities/common/serialized_value.py +1 -1
  7. datahub/api/entities/corpgroup/corpgroup.py +1 -1
  8. datahub/api/entities/dataproduct/dataproduct.py +32 -3
  9. datahub/api/entities/dataset/dataset.py +26 -23
  10. datahub/api/entities/external/__init__.py +0 -0
  11. datahub/api/entities/external/external_entities.py +724 -0
  12. datahub/api/entities/external/external_tag.py +147 -0
  13. datahub/api/entities/external/lake_formation_external_entites.py +162 -0
  14. datahub/api/entities/external/restricted_text.py +172 -0
  15. datahub/api/entities/external/unity_catalog_external_entites.py +172 -0
  16. datahub/api/entities/forms/forms.py +3 -3
  17. datahub/api/entities/structuredproperties/structuredproperties.py +4 -4
  18. datahub/api/graphql/operation.py +10 -6
  19. datahub/cli/check_cli.py +88 -7
  20. datahub/cli/cli_utils.py +63 -0
  21. datahub/cli/config_utils.py +18 -10
  22. datahub/cli/container_cli.py +5 -0
  23. datahub/cli/delete_cli.py +125 -27
  24. datahub/cli/docker_check.py +110 -14
  25. datahub/cli/docker_cli.py +153 -229
  26. datahub/cli/exists_cli.py +0 -2
  27. datahub/cli/get_cli.py +0 -2
  28. datahub/cli/graphql_cli.py +1422 -0
  29. datahub/cli/iceberg_cli.py +5 -0
  30. datahub/cli/ingest_cli.py +3 -15
  31. datahub/cli/migrate.py +2 -0
  32. datahub/cli/put_cli.py +1 -4
  33. datahub/cli/quickstart_versioning.py +53 -10
  34. datahub/cli/specific/assertions_cli.py +37 -6
  35. datahub/cli/specific/datacontract_cli.py +54 -7
  36. datahub/cli/specific/dataproduct_cli.py +2 -15
  37. datahub/cli/specific/dataset_cli.py +1 -8
  38. datahub/cli/specific/forms_cli.py +0 -4
  39. datahub/cli/specific/group_cli.py +0 -2
  40. datahub/cli/specific/structuredproperties_cli.py +1 -4
  41. datahub/cli/specific/user_cli.py +172 -3
  42. datahub/cli/state_cli.py +0 -2
  43. datahub/cli/timeline_cli.py +0 -2
  44. datahub/configuration/common.py +40 -1
  45. datahub/configuration/connection_resolver.py +5 -2
  46. datahub/configuration/env_vars.py +331 -0
  47. datahub/configuration/import_resolver.py +7 -4
  48. datahub/configuration/kafka.py +21 -1
  49. datahub/configuration/pydantic_migration_helpers.py +6 -13
  50. datahub/configuration/source_common.py +3 -2
  51. datahub/configuration/validate_field_deprecation.py +5 -2
  52. datahub/configuration/validate_field_removal.py +8 -2
  53. datahub/configuration/validate_field_rename.py +6 -5
  54. datahub/configuration/validate_multiline_string.py +5 -2
  55. datahub/emitter/mce_builder.py +8 -4
  56. datahub/emitter/rest_emitter.py +103 -30
  57. datahub/entrypoints.py +6 -3
  58. datahub/ingestion/api/auto_work_units/auto_ensure_aspect_size.py +297 -1
  59. datahub/ingestion/api/auto_work_units/auto_validate_input_fields.py +87 -0
  60. datahub/ingestion/api/decorators.py +15 -3
  61. datahub/ingestion/api/report.py +381 -3
  62. datahub/ingestion/api/sink.py +27 -2
  63. datahub/ingestion/api/source.py +165 -58
  64. datahub/ingestion/api/source_protocols.py +23 -0
  65. datahub/ingestion/autogenerated/__init__.py +0 -0
  66. datahub/ingestion/autogenerated/capability_summary.json +3652 -0
  67. datahub/ingestion/autogenerated/lineage.json +402 -0
  68. datahub/ingestion/autogenerated/lineage_helper.py +177 -0
  69. datahub/ingestion/extractor/schema_util.py +13 -4
  70. datahub/ingestion/glossary/classification_mixin.py +5 -0
  71. datahub/ingestion/graph/client.py +330 -25
  72. datahub/ingestion/graph/config.py +3 -2
  73. datahub/ingestion/graph/filters.py +30 -11
  74. datahub/ingestion/reporting/datahub_ingestion_run_summary_provider.py +21 -11
  75. datahub/ingestion/run/pipeline.py +81 -11
  76. datahub/ingestion/run/pipeline_config.py +2 -2
  77. datahub/ingestion/sink/datahub_kafka.py +1 -0
  78. datahub/ingestion/sink/datahub_rest.py +13 -5
  79. datahub/ingestion/sink/file.py +1 -0
  80. datahub/ingestion/source/abs/config.py +1 -1
  81. datahub/ingestion/source/abs/datalake_profiler_config.py +1 -1
  82. datahub/ingestion/source/abs/source.py +15 -30
  83. datahub/ingestion/source/aws/aws_common.py +185 -13
  84. datahub/ingestion/source/aws/glue.py +517 -244
  85. datahub/ingestion/source/aws/platform_resource_repository.py +30 -0
  86. datahub/ingestion/source/aws/s3_boto_utils.py +100 -5
  87. datahub/ingestion/source/aws/tag_entities.py +270 -0
  88. datahub/ingestion/source/azure/azure_common.py +3 -3
  89. datahub/ingestion/source/bigquery_v2/bigquery.py +67 -24
  90. datahub/ingestion/source/bigquery_v2/bigquery_config.py +47 -19
  91. datahub/ingestion/source/bigquery_v2/bigquery_connection.py +12 -1
  92. datahub/ingestion/source/bigquery_v2/bigquery_queries.py +3 -0
  93. datahub/ingestion/source/bigquery_v2/bigquery_report.py +0 -2
  94. datahub/ingestion/source/bigquery_v2/bigquery_schema.py +23 -16
  95. datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py +20 -5
  96. datahub/ingestion/source/bigquery_v2/common.py +1 -1
  97. datahub/ingestion/source/bigquery_v2/profiler.py +4 -2
  98. datahub/ingestion/source/bigquery_v2/queries.py +3 -3
  99. datahub/ingestion/source/bigquery_v2/queries_extractor.py +45 -9
  100. datahub/ingestion/source/cassandra/cassandra.py +6 -8
  101. datahub/ingestion/source/cassandra/cassandra_api.py +17 -1
  102. datahub/ingestion/source/cassandra/cassandra_config.py +5 -0
  103. datahub/ingestion/source/cassandra/cassandra_profiling.py +7 -6
  104. datahub/ingestion/source/cassandra/cassandra_utils.py +1 -2
  105. datahub/ingestion/source/common/gcp_credentials_config.py +3 -1
  106. datahub/ingestion/source/common/subtypes.py +53 -0
  107. datahub/ingestion/source/data_lake_common/data_lake_utils.py +37 -0
  108. datahub/ingestion/source/data_lake_common/object_store.py +115 -27
  109. datahub/ingestion/source/data_lake_common/path_spec.py +72 -43
  110. datahub/ingestion/source/datahub/config.py +12 -9
  111. datahub/ingestion/source/datahub/datahub_database_reader.py +26 -11
  112. datahub/ingestion/source/datahub/datahub_source.py +10 -0
  113. datahub/ingestion/source/dbt/dbt_cloud.py +16 -5
  114. datahub/ingestion/source/dbt/dbt_common.py +224 -9
  115. datahub/ingestion/source/dbt/dbt_core.py +3 -0
  116. datahub/ingestion/source/debug/__init__.py +0 -0
  117. datahub/ingestion/source/debug/datahub_debug.py +300 -0
  118. datahub/ingestion/source/delta_lake/config.py +9 -5
  119. datahub/ingestion/source/delta_lake/source.py +8 -0
  120. datahub/ingestion/source/dremio/dremio_api.py +114 -73
  121. datahub/ingestion/source/dremio/dremio_aspects.py +3 -2
  122. datahub/ingestion/source/dremio/dremio_config.py +5 -4
  123. datahub/ingestion/source/dremio/dremio_reporting.py +22 -3
  124. datahub/ingestion/source/dremio/dremio_source.py +132 -98
  125. datahub/ingestion/source/dremio/dremio_sql_queries.py +82 -21
  126. datahub/ingestion/source/dynamodb/dynamodb.py +11 -8
  127. datahub/ingestion/source/excel/__init__.py +0 -0
  128. datahub/ingestion/source/excel/config.py +92 -0
  129. datahub/ingestion/source/excel/excel_file.py +539 -0
  130. datahub/ingestion/source/excel/profiling.py +308 -0
  131. datahub/ingestion/source/excel/report.py +49 -0
  132. datahub/ingestion/source/excel/source.py +662 -0
  133. datahub/ingestion/source/excel/util.py +18 -0
  134. datahub/ingestion/source/feast.py +8 -10
  135. datahub/ingestion/source/file.py +3 -0
  136. datahub/ingestion/source/fivetran/config.py +66 -7
  137. datahub/ingestion/source/fivetran/fivetran.py +227 -43
  138. datahub/ingestion/source/fivetran/fivetran_log_api.py +37 -8
  139. datahub/ingestion/source/fivetran/fivetran_query.py +51 -29
  140. datahub/ingestion/source/fivetran/fivetran_rest_api.py +65 -0
  141. datahub/ingestion/source/fivetran/response_models.py +97 -0
  142. datahub/ingestion/source/gc/datahub_gc.py +0 -2
  143. datahub/ingestion/source/gcs/gcs_source.py +32 -4
  144. datahub/ingestion/source/ge_data_profiler.py +108 -31
  145. datahub/ingestion/source/ge_profiling_config.py +26 -11
  146. datahub/ingestion/source/grafana/entity_mcp_builder.py +272 -0
  147. datahub/ingestion/source/grafana/field_utils.py +307 -0
  148. datahub/ingestion/source/grafana/grafana_api.py +142 -0
  149. datahub/ingestion/source/grafana/grafana_config.py +104 -0
  150. datahub/ingestion/source/grafana/grafana_source.py +522 -84
  151. datahub/ingestion/source/grafana/lineage.py +202 -0
  152. datahub/ingestion/source/grafana/models.py +137 -0
  153. datahub/ingestion/source/grafana/report.py +90 -0
  154. datahub/ingestion/source/grafana/types.py +16 -0
  155. datahub/ingestion/source/hex/api.py +28 -1
  156. datahub/ingestion/source/hex/hex.py +16 -5
  157. datahub/ingestion/source/hex/mapper.py +16 -2
  158. datahub/ingestion/source/hex/model.py +2 -0
  159. datahub/ingestion/source/hex/query_fetcher.py +1 -1
  160. datahub/ingestion/source/iceberg/iceberg.py +123 -59
  161. datahub/ingestion/source/iceberg/iceberg_profiler.py +4 -2
  162. datahub/ingestion/source/identity/azure_ad.py +1 -1
  163. datahub/ingestion/source/identity/okta.py +1 -14
  164. datahub/ingestion/source/kafka/kafka.py +16 -0
  165. datahub/ingestion/source/kafka_connect/common.py +2 -2
  166. datahub/ingestion/source/kafka_connect/sink_connectors.py +156 -47
  167. datahub/ingestion/source/kafka_connect/source_connectors.py +62 -4
  168. datahub/ingestion/source/looker/looker_common.py +148 -79
  169. datahub/ingestion/source/looker/looker_config.py +15 -4
  170. datahub/ingestion/source/looker/looker_constant.py +4 -0
  171. datahub/ingestion/source/looker/looker_lib_wrapper.py +36 -3
  172. datahub/ingestion/source/looker/looker_liquid_tag.py +56 -5
  173. datahub/ingestion/source/looker/looker_source.py +503 -547
  174. datahub/ingestion/source/looker/looker_view_id_cache.py +1 -1
  175. datahub/ingestion/source/looker/lookml_concept_context.py +1 -1
  176. datahub/ingestion/source/looker/lookml_config.py +31 -3
  177. datahub/ingestion/source/looker/lookml_refinement.py +1 -1
  178. datahub/ingestion/source/looker/lookml_source.py +96 -117
  179. datahub/ingestion/source/looker/view_upstream.py +494 -1
  180. datahub/ingestion/source/metabase.py +32 -6
  181. datahub/ingestion/source/metadata/business_glossary.py +7 -7
  182. datahub/ingestion/source/metadata/lineage.py +9 -9
  183. datahub/ingestion/source/mlflow.py +12 -2
  184. datahub/ingestion/source/mock_data/__init__.py +0 -0
  185. datahub/ingestion/source/mock_data/datahub_mock_data.py +533 -0
  186. datahub/ingestion/source/mock_data/datahub_mock_data_report.py +12 -0
  187. datahub/ingestion/source/mock_data/table_naming_helper.py +97 -0
  188. datahub/ingestion/source/mode.py +26 -5
  189. datahub/ingestion/source/mongodb.py +11 -1
  190. datahub/ingestion/source/neo4j/neo4j_source.py +83 -144
  191. datahub/ingestion/source/nifi.py +2 -2
  192. datahub/ingestion/source/openapi.py +1 -1
  193. datahub/ingestion/source/powerbi/config.py +47 -21
  194. datahub/ingestion/source/powerbi/m_query/data_classes.py +1 -0
  195. datahub/ingestion/source/powerbi/m_query/parser.py +2 -2
  196. datahub/ingestion/source/powerbi/m_query/pattern_handler.py +100 -10
  197. datahub/ingestion/source/powerbi/powerbi.py +10 -6
  198. datahub/ingestion/source/powerbi/rest_api_wrapper/powerbi_api.py +0 -1
  199. datahub/ingestion/source/powerbi_report_server/report_server.py +0 -23
  200. datahub/ingestion/source/powerbi_report_server/report_server_domain.py +2 -4
  201. datahub/ingestion/source/preset.py +3 -3
  202. datahub/ingestion/source/qlik_sense/data_classes.py +28 -8
  203. datahub/ingestion/source/qlik_sense/qlik_sense.py +2 -1
  204. datahub/ingestion/source/redash.py +1 -1
  205. datahub/ingestion/source/redshift/config.py +15 -9
  206. datahub/ingestion/source/redshift/datashares.py +1 -1
  207. datahub/ingestion/source/redshift/lineage.py +386 -687
  208. datahub/ingestion/source/redshift/query.py +23 -19
  209. datahub/ingestion/source/redshift/redshift.py +52 -111
  210. datahub/ingestion/source/redshift/redshift_schema.py +17 -12
  211. datahub/ingestion/source/redshift/report.py +0 -2
  212. datahub/ingestion/source/redshift/usage.py +6 -5
  213. datahub/ingestion/source/s3/report.py +4 -2
  214. datahub/ingestion/source/s3/source.py +449 -248
  215. datahub/ingestion/source/sac/sac.py +3 -1
  216. datahub/ingestion/source/salesforce.py +28 -13
  217. datahub/ingestion/source/schema/json_schema.py +14 -14
  218. datahub/ingestion/source/schema_inference/object.py +22 -6
  219. datahub/ingestion/source/sigma/data_classes.py +3 -0
  220. datahub/ingestion/source/sigma/sigma.py +7 -1
  221. datahub/ingestion/source/slack/slack.py +10 -16
  222. datahub/ingestion/source/snaplogic/__init__.py +0 -0
  223. datahub/ingestion/source/snaplogic/snaplogic.py +355 -0
  224. datahub/ingestion/source/snaplogic/snaplogic_config.py +37 -0
  225. datahub/ingestion/source/snaplogic/snaplogic_lineage_extractor.py +107 -0
  226. datahub/ingestion/source/snaplogic/snaplogic_parser.py +168 -0
  227. datahub/ingestion/source/snaplogic/snaplogic_utils.py +31 -0
  228. datahub/ingestion/source/snowflake/constants.py +3 -0
  229. datahub/ingestion/source/snowflake/snowflake_config.py +76 -23
  230. datahub/ingestion/source/snowflake/snowflake_connection.py +24 -8
  231. datahub/ingestion/source/snowflake/snowflake_lineage_v2.py +19 -6
  232. datahub/ingestion/source/snowflake/snowflake_queries.py +464 -97
  233. datahub/ingestion/source/snowflake/snowflake_query.py +77 -5
  234. datahub/ingestion/source/snowflake/snowflake_report.py +1 -2
  235. datahub/ingestion/source/snowflake/snowflake_schema.py +352 -16
  236. datahub/ingestion/source/snowflake/snowflake_schema_gen.py +51 -10
  237. datahub/ingestion/source/snowflake/snowflake_summary.py +7 -1
  238. datahub/ingestion/source/snowflake/snowflake_usage_v2.py +8 -2
  239. datahub/ingestion/source/snowflake/snowflake_utils.py +36 -15
  240. datahub/ingestion/source/snowflake/snowflake_v2.py +39 -4
  241. datahub/ingestion/source/snowflake/stored_proc_lineage.py +143 -0
  242. datahub/ingestion/source/sql/athena.py +217 -25
  243. datahub/ingestion/source/sql/athena_properties_extractor.py +795 -0
  244. datahub/ingestion/source/sql/clickhouse.py +24 -8
  245. datahub/ingestion/source/sql/cockroachdb.py +5 -4
  246. datahub/ingestion/source/sql/druid.py +2 -2
  247. datahub/ingestion/source/sql/hana.py +3 -1
  248. datahub/ingestion/source/sql/hive.py +4 -3
  249. datahub/ingestion/source/sql/hive_metastore.py +19 -20
  250. datahub/ingestion/source/sql/mariadb.py +0 -1
  251. datahub/ingestion/source/sql/mssql/job_models.py +3 -1
  252. datahub/ingestion/source/sql/mssql/source.py +336 -57
  253. datahub/ingestion/source/sql/mysql.py +154 -4
  254. datahub/ingestion/source/sql/oracle.py +5 -5
  255. datahub/ingestion/source/sql/postgres.py +142 -6
  256. datahub/ingestion/source/sql/presto.py +2 -1
  257. datahub/ingestion/source/sql/sql_common.py +281 -49
  258. datahub/ingestion/source/sql/sql_generic_profiler.py +2 -1
  259. datahub/ingestion/source/sql/sql_types.py +22 -0
  260. datahub/ingestion/source/sql/sqlalchemy_uri.py +39 -7
  261. datahub/ingestion/source/sql/teradata.py +1028 -245
  262. datahub/ingestion/source/sql/trino.py +11 -1
  263. datahub/ingestion/source/sql/two_tier_sql_source.py +2 -3
  264. datahub/ingestion/source/sql/vertica.py +14 -7
  265. datahub/ingestion/source/sql_queries.py +219 -121
  266. datahub/ingestion/source/state/checkpoint.py +8 -29
  267. datahub/ingestion/source/state/entity_removal_state.py +5 -2
  268. datahub/ingestion/source/state/redundant_run_skip_handler.py +21 -0
  269. datahub/ingestion/source/state/stateful_ingestion_base.py +36 -11
  270. datahub/ingestion/source/superset.py +314 -67
  271. datahub/ingestion/source/tableau/tableau.py +135 -59
  272. datahub/ingestion/source/tableau/tableau_common.py +9 -2
  273. datahub/ingestion/source/tableau/tableau_constant.py +1 -4
  274. datahub/ingestion/source/tableau/tableau_server_wrapper.py +3 -0
  275. datahub/ingestion/source/unity/config.py +160 -40
  276. datahub/ingestion/source/unity/connection.py +61 -0
  277. datahub/ingestion/source/unity/connection_test.py +1 -0
  278. datahub/ingestion/source/unity/platform_resource_repository.py +19 -0
  279. datahub/ingestion/source/unity/proxy.py +794 -51
  280. datahub/ingestion/source/unity/proxy_patch.py +321 -0
  281. datahub/ingestion/source/unity/proxy_types.py +36 -2
  282. datahub/ingestion/source/unity/report.py +15 -3
  283. datahub/ingestion/source/unity/source.py +465 -131
  284. datahub/ingestion/source/unity/tag_entities.py +197 -0
  285. datahub/ingestion/source/unity/usage.py +46 -4
  286. datahub/ingestion/source/usage/clickhouse_usage.py +4 -1
  287. datahub/ingestion/source/usage/starburst_trino_usage.py +5 -2
  288. datahub/ingestion/source/usage/usage_common.py +4 -3
  289. datahub/ingestion/source/vertexai/vertexai.py +1 -1
  290. datahub/ingestion/source_config/pulsar.py +3 -1
  291. datahub/ingestion/source_report/ingestion_stage.py +50 -11
  292. datahub/ingestion/transformer/add_dataset_ownership.py +18 -2
  293. datahub/ingestion/transformer/base_transformer.py +8 -5
  294. datahub/ingestion/transformer/set_browse_path.py +112 -0
  295. datahub/integrations/assertion/snowflake/compiler.py +4 -3
  296. datahub/metadata/_internal_schema_classes.py +6806 -4871
  297. datahub/metadata/_urns/urn_defs.py +1767 -1539
  298. datahub/metadata/com/linkedin/pegasus2avro/application/__init__.py +19 -0
  299. datahub/metadata/com/linkedin/pegasus2avro/common/__init__.py +2 -0
  300. datahub/metadata/com/linkedin/pegasus2avro/file/__init__.py +19 -0
  301. datahub/metadata/com/linkedin/pegasus2avro/identity/__init__.py +2 -0
  302. datahub/metadata/com/linkedin/pegasus2avro/logical/__init__.py +15 -0
  303. datahub/metadata/com/linkedin/pegasus2avro/metadata/key/__init__.py +6 -0
  304. datahub/metadata/com/linkedin/pegasus2avro/module/__init__.py +31 -0
  305. datahub/metadata/com/linkedin/pegasus2avro/platform/event/v1/__init__.py +4 -0
  306. datahub/metadata/com/linkedin/pegasus2avro/role/__init__.py +2 -0
  307. datahub/metadata/com/linkedin/pegasus2avro/settings/asset/__init__.py +19 -0
  308. datahub/metadata/com/linkedin/pegasus2avro/settings/global/__init__.py +8 -0
  309. datahub/metadata/com/linkedin/pegasus2avro/template/__init__.py +31 -0
  310. datahub/metadata/schema.avsc +18395 -16979
  311. datahub/metadata/schemas/Actors.avsc +38 -1
  312. datahub/metadata/schemas/ApplicationKey.avsc +31 -0
  313. datahub/metadata/schemas/ApplicationProperties.avsc +72 -0
  314. datahub/metadata/schemas/Applications.avsc +38 -0
  315. datahub/metadata/schemas/AssetSettings.avsc +63 -0
  316. datahub/metadata/schemas/ChartInfo.avsc +2 -1
  317. datahub/metadata/schemas/ChartKey.avsc +1 -0
  318. datahub/metadata/schemas/ContainerKey.avsc +1 -0
  319. datahub/metadata/schemas/ContainerProperties.avsc +8 -0
  320. datahub/metadata/schemas/CorpUserEditableInfo.avsc +1 -1
  321. datahub/metadata/schemas/CorpUserSettings.avsc +50 -0
  322. datahub/metadata/schemas/DashboardKey.avsc +1 -0
  323. datahub/metadata/schemas/DataFlowInfo.avsc +8 -0
  324. datahub/metadata/schemas/DataFlowKey.avsc +1 -0
  325. datahub/metadata/schemas/DataHubFileInfo.avsc +230 -0
  326. datahub/metadata/schemas/DataHubFileKey.avsc +21 -0
  327. datahub/metadata/schemas/DataHubPageModuleKey.avsc +21 -0
  328. datahub/metadata/schemas/DataHubPageModuleProperties.avsc +298 -0
  329. datahub/metadata/schemas/DataHubPageTemplateKey.avsc +21 -0
  330. datahub/metadata/schemas/DataHubPageTemplateProperties.avsc +251 -0
  331. datahub/metadata/schemas/DataHubPolicyInfo.avsc +12 -1
  332. datahub/metadata/schemas/DataJobInfo.avsc +8 -0
  333. datahub/metadata/schemas/DataJobInputOutput.avsc +8 -0
  334. datahub/metadata/schemas/DataJobKey.avsc +1 -0
  335. datahub/metadata/schemas/DataProcessKey.avsc +8 -0
  336. datahub/metadata/schemas/DataProductKey.avsc +3 -1
  337. datahub/metadata/schemas/DataProductProperties.avsc +1 -1
  338. datahub/metadata/schemas/DatasetKey.avsc +11 -1
  339. datahub/metadata/schemas/DatasetUsageStatistics.avsc +8 -0
  340. datahub/metadata/schemas/DomainKey.avsc +2 -1
  341. datahub/metadata/schemas/GlobalSettingsInfo.avsc +134 -0
  342. datahub/metadata/schemas/GlossaryNodeKey.avsc +2 -1
  343. datahub/metadata/schemas/GlossaryTermKey.avsc +3 -1
  344. datahub/metadata/schemas/IcebergWarehouseInfo.avsc +8 -0
  345. datahub/metadata/schemas/IncidentInfo.avsc +3 -3
  346. datahub/metadata/schemas/InstitutionalMemory.avsc +31 -0
  347. datahub/metadata/schemas/LogicalParent.avsc +145 -0
  348. datahub/metadata/schemas/MLFeatureKey.avsc +1 -0
  349. datahub/metadata/schemas/MLFeatureTableKey.avsc +1 -0
  350. datahub/metadata/schemas/MLModelDeploymentKey.avsc +8 -0
  351. datahub/metadata/schemas/MLModelGroupKey.avsc +11 -1
  352. datahub/metadata/schemas/MLModelKey.avsc +9 -0
  353. datahub/metadata/schemas/MLPrimaryKeyKey.avsc +1 -0
  354. datahub/metadata/schemas/MetadataChangeEvent.avsc +151 -47
  355. datahub/metadata/schemas/MetadataChangeLog.avsc +62 -44
  356. datahub/metadata/schemas/MetadataChangeProposal.avsc +61 -0
  357. datahub/metadata/schemas/NotebookKey.avsc +1 -0
  358. datahub/metadata/schemas/Operation.avsc +4 -2
  359. datahub/metadata/schemas/Ownership.avsc +69 -0
  360. datahub/metadata/schemas/QuerySubjects.avsc +1 -12
  361. datahub/metadata/schemas/RelationshipChangeEvent.avsc +215 -0
  362. datahub/metadata/schemas/SchemaFieldKey.avsc +4 -1
  363. datahub/metadata/schemas/StructuredProperties.avsc +69 -0
  364. datahub/metadata/schemas/StructuredPropertySettings.avsc +9 -0
  365. datahub/metadata/schemas/SystemMetadata.avsc +61 -0
  366. datahub/metadata/schemas/UpstreamLineage.avsc +9 -0
  367. datahub/sdk/__init__.py +2 -0
  368. datahub/sdk/_all_entities.py +7 -0
  369. datahub/sdk/_shared.py +249 -5
  370. datahub/sdk/chart.py +386 -0
  371. datahub/sdk/container.py +7 -0
  372. datahub/sdk/dashboard.py +453 -0
  373. datahub/sdk/dataflow.py +7 -0
  374. datahub/sdk/datajob.py +45 -13
  375. datahub/sdk/dataset.py +56 -2
  376. datahub/sdk/entity_client.py +111 -9
  377. datahub/sdk/lineage_client.py +663 -82
  378. datahub/sdk/main_client.py +50 -16
  379. datahub/sdk/mlmodel.py +120 -38
  380. datahub/sdk/mlmodelgroup.py +7 -0
  381. datahub/sdk/search_client.py +7 -3
  382. datahub/sdk/search_filters.py +304 -36
  383. datahub/secret/datahub_secret_store.py +3 -0
  384. datahub/secret/environment_secret_store.py +29 -0
  385. datahub/secret/file_secret_store.py +49 -0
  386. datahub/specific/aspect_helpers/fine_grained_lineage.py +76 -0
  387. datahub/specific/aspect_helpers/siblings.py +73 -0
  388. datahub/specific/aspect_helpers/structured_properties.py +27 -0
  389. datahub/specific/chart.py +1 -1
  390. datahub/specific/datajob.py +15 -1
  391. datahub/specific/dataproduct.py +4 -0
  392. datahub/specific/dataset.py +39 -59
  393. datahub/sql_parsing/split_statements.py +13 -0
  394. datahub/sql_parsing/sql_parsing_aggregator.py +70 -26
  395. datahub/sql_parsing/sqlglot_lineage.py +196 -42
  396. datahub/sql_parsing/sqlglot_utils.py +12 -4
  397. datahub/sql_parsing/tool_meta_extractor.py +1 -3
  398. datahub/telemetry/telemetry.py +28 -14
  399. datahub/testing/sdk_v2_helpers.py +7 -1
  400. datahub/upgrade/upgrade.py +73 -17
  401. datahub/utilities/file_backed_collections.py +8 -9
  402. datahub/utilities/is_pytest.py +3 -2
  403. datahub/utilities/logging_manager.py +22 -6
  404. datahub/utilities/mapping.py +29 -2
  405. datahub/utilities/sample_data.py +5 -4
  406. datahub/utilities/server_config_util.py +10 -1
  407. datahub/utilities/sqlalchemy_query_combiner.py +5 -2
  408. datahub/utilities/stats_collections.py +4 -0
  409. datahub/utilities/urns/urn.py +41 -2
  410. datahub/emitter/sql_parsing_builder.py +0 -306
  411. datahub/ingestion/source/redshift/lineage_v2.py +0 -466
  412. {acryl_datahub-1.1.1rc4.dist-info → acryl_datahub-1.3.0.1rc9.dist-info}/WHEEL +0 -0
  413. {acryl_datahub-1.1.1rc4.dist-info → acryl_datahub-1.3.0.1rc9.dist-info}/licenses/LICENSE +0 -0
  414. {acryl_datahub-1.1.1rc4.dist-info → acryl_datahub-1.3.0.1rc9.dist-info}/top_level.txt +0 -0
@@ -1,8 +1,9 @@
1
1
  import enum
2
2
  import os
3
+ import pathlib
3
4
  from contextlib import contextmanager
4
5
  from dataclasses import dataclass
5
- from typing import Any, Dict, Iterator, List, Optional
6
+ from typing import Any, Dict, Iterator, List, Optional, Set
6
7
 
7
8
  import docker
8
9
  import docker.errors
@@ -10,11 +11,13 @@ import docker.models.containers
10
11
  import yaml
11
12
 
12
13
  from datahub.configuration.common import ExceptionWithProps
14
+ from datahub.configuration.env_vars import get_compose_project_name
13
15
 
14
16
  # Docker seems to under-report memory allocated, so we also need a bit of buffer to account for it.
15
- MIN_MEMORY_NEEDED = 3.8 # GB
17
+ MIN_MEMORY_NEEDED = 4.3 # GB
18
+ MIN_DISK_SPACE_NEEDED = 13 # GB
16
19
 
17
- DOCKER_COMPOSE_PROJECT_NAME = os.getenv("DATAHUB_COMPOSE_PROJECT_NAME", "datahub")
20
+ DOCKER_COMPOSE_PROJECT_NAME = get_compose_project_name()
18
21
  DATAHUB_COMPOSE_PROJECT_FILTER = {
19
22
  "label": f"com.docker.compose.project={DOCKER_COMPOSE_PROJECT_NAME}"
20
23
  }
@@ -37,6 +40,10 @@ class DockerLowMemoryError(Exception):
37
40
  SHOW_STACK_TRACE = False
38
41
 
39
42
 
43
+ class DockerLowDiskSpaceError(Exception):
44
+ SHOW_STACK_TRACE = False
45
+
46
+
40
47
  class DockerComposeVersionError(Exception):
41
48
  SHOW_STACK_TRACE = False
42
49
 
@@ -102,6 +109,24 @@ def run_quickstart_preflight_checks(client: docker.DockerClient) -> None:
102
109
  "You can increase the memory allocated to Docker in the Docker settings."
103
110
  )
104
111
 
112
+ result = client.containers.run(
113
+ "alpine:latest",
114
+ "sh -c \"df -B1 -P / | awk 'NR==2{print $2, $4}'\"", # total, available
115
+ remove=True,
116
+ stdout=True,
117
+ stderr=True,
118
+ )
119
+
120
+ output = result.decode("utf-8").strip()
121
+ total_bytes, available_bytes = map(int, output.split())
122
+
123
+ available_gb = available_bytes / (1024**3)
124
+ if available_gb < MIN_DISK_SPACE_NEEDED:
125
+ raise DockerLowDiskSpaceError(
126
+ f"Total Docker disk space available {available_gb:.2f}GB is below the minimum threshold {MIN_DISK_SPACE_NEEDED}GB. "
127
+ "You can increase the disk space allocated to Docker in the Docker settings or free up disk space`"
128
+ )
129
+
105
130
 
106
131
  class ContainerStatus(enum.Enum):
107
132
  OK = "is ok"
@@ -126,10 +151,24 @@ class DockerContainerStatus:
126
151
  @dataclass
127
152
  class QuickstartStatus:
128
153
  containers: List[DockerContainerStatus]
154
+ volumes: Set[str]
155
+ # On moving to compose profiles, this CLI will no longer support running quickstart instances from earlier versions.
156
+ # While the check command can work, upgrades or
157
+ running_unsupported_version: bool
158
+
159
+ def __init__(
160
+ self,
161
+ containers: List[DockerContainerStatus],
162
+ volumes: List[str],
163
+ running_unsupported_version: bool = False,
164
+ ):
165
+ self.containers = containers
166
+ self.running_unsupported_version = running_unsupported_version
167
+ self.volumes = set(volumes)
129
168
 
130
169
  def errors(self) -> List[str]:
131
170
  if not self.containers:
132
- return ["quickstart.sh or dev.sh is not running"]
171
+ return ["datahub is not running"]
133
172
 
134
173
  return [
135
174
  f"{container.name} {container.status.value}"
@@ -176,6 +215,26 @@ class QuickstartStatus:
176
215
  },
177
216
  )
178
217
 
218
+ def get_containers(self) -> Set[str]:
219
+ if self.containers:
220
+ return {container.name for container in self.containers}
221
+ else:
222
+ return set()
223
+
224
+
225
+ def detect_legacy_quickstart_compose(containers: Set[str]) -> bool:
226
+ return "zookeeper" in containers
227
+
228
+
229
+ def _get_services_from_compose(compose_file: str) -> Set[str]:
230
+ with open(compose_file) as config_file:
231
+ return yaml.safe_load(config_file).get("services", {}).keys()
232
+
233
+
234
+ def _get_volumes_from_compose(compose_file: str) -> Set[str]:
235
+ with open(compose_file) as config_file:
236
+ return yaml.safe_load(config_file).get("volumes", {}).keys()
237
+
179
238
 
180
239
  def check_docker_quickstart() -> QuickstartStatus:
181
240
  container_statuses: List[DockerContainerStatus] = []
@@ -188,7 +247,7 @@ def check_docker_quickstart() -> QuickstartStatus:
188
247
  ignore_removed=True,
189
248
  )
190
249
  if len(containers) == 0:
191
- return QuickstartStatus([])
250
+ return QuickstartStatus([], [], running_unsupported_version=False)
192
251
 
193
252
  # load the expected containers from the docker-compose file
194
253
  config_files = (
@@ -197,16 +256,17 @@ def check_docker_quickstart() -> QuickstartStatus:
197
256
  .split(",")
198
257
  )
199
258
 
200
- # If using profiles, alternative check
259
+ # If using profiles, alternative check ##TODO: Does this really work? Check mixpanel for usage of this.
201
260
  if config_files and "/profiles/" in config_files[0]:
202
261
  return check_docker_quickstart_profiles(client)
203
262
 
204
263
  all_containers = set()
205
264
  for config_file in config_files:
206
- with open(config_file) as config_file:
207
- all_containers.update(
208
- yaml.safe_load(config_file).get("services", {}).keys()
209
- )
265
+ all_containers.update(_get_services_from_compose(config_file))
266
+
267
+ all_volumes = set()
268
+ for config_file in config_files:
269
+ all_volumes.update(_get_volumes_from_compose(config_file))
210
270
 
211
271
  existing_containers = set()
212
272
  # Check that the containers are running and healthy.
@@ -240,8 +300,12 @@ def check_docker_quickstart() -> QuickstartStatus:
240
300
  container_statuses.append(
241
301
  DockerContainerStatus(missing, ContainerStatus.MISSING)
242
302
  )
243
-
244
- return QuickstartStatus(container_statuses)
303
+ running_unsupported_version = detect_legacy_quickstart_compose(all_containers)
304
+ return QuickstartStatus(
305
+ containers=container_statuses,
306
+ volumes=list(all_volumes),
307
+ running_unsupported_version=running_unsupported_version,
308
+ )
245
309
 
246
310
 
247
311
  def check_docker_quickstart_profiles(client: docker.DockerClient) -> QuickstartStatus:
@@ -254,7 +318,7 @@ def check_docker_quickstart_profiles(client: docker.DockerClient) -> QuickstartS
254
318
  ignore_removed=True,
255
319
  )
256
320
  if len(containers) == 0:
257
- return QuickstartStatus([])
321
+ return QuickstartStatus([], [], running_unsupported_version=False)
258
322
 
259
323
  existing_containers = set()
260
324
  # Check that the containers are running and healthy.
@@ -273,4 +337,36 @@ def check_docker_quickstart_profiles(client: docker.DockerClient) -> QuickstartS
273
337
 
274
338
  container_statuses.append(DockerContainerStatus(name, status))
275
339
 
276
- return QuickstartStatus(container_statuses)
340
+ # TODO: Can this be handled with older verions?
341
+ return QuickstartStatus(
342
+ container_statuses, volumes=[], running_unsupported_version=False
343
+ )
344
+
345
+
346
+ def check_upgrade_supported(
347
+ quickstart_compose_file: List[pathlib.Path], quickstart_status: QuickstartStatus
348
+ ) -> bool:
349
+ if (
350
+ quickstart_status.running_unsupported_version
351
+ ): # we detected a legacy quickstart service
352
+ return False
353
+
354
+ if not quickstart_status.get_containers(): # no containers are running
355
+ return True
356
+
357
+ compose_services = set()
358
+ compose_volumes = set()
359
+
360
+ for compose_file in quickstart_compose_file:
361
+ compose_services.update(_get_services_from_compose(str(compose_file)))
362
+ compose_volumes.update(_get_volumes_from_compose(str(compose_file)))
363
+
364
+ # if all services and volumes are not the same, the state in the volumes may not be compatible with the new services.
365
+ # We are checking for containers and volumes per the compose file, not necessarily all of them being present
366
+ if (
367
+ compose_services == quickstart_status.get_containers()
368
+ and compose_volumes == quickstart_status.volumes
369
+ ):
370
+ return True
371
+ else:
372
+ return False